| 近红外光谱技术结合支持向量机法在保水剂鉴别工作中的应用 |
| |
| 引用本文： | 岳征文,王红柳,成格尔,赵铭军,王百田.近红外光谱技术结合支持向量机法在保水剂鉴别工作中的应用[J].干旱区资源与环境,2012(4):172-175. |
| |
| 作者姓名： | 岳征文 王红柳 成格尔 赵铭军 王百田 |
| |
| 作者单位： | 北京林业大学水土保持学院;北京林业大学草地资源与生态实验室;内蒙古农业大学生态环境学院;中国石化管道储运公司徐州输油处 |
| |
| 基金项目： | 国家"十一五"科技支撑计划(2006BAD03A0301)困难立地工程造林新材料、新产品及应用技术;林业行业公益项目(200704031)资助 |
| |
| 摘 要： | 基于近红外光谱技术结合应用主成分回归法(PCR)、偏最小二乘法(PLS)、BP神经网络法、支持向量机(SVM)等四种方法对来自不同国家和地区的24种聚丙烯-聚丙烯酰胺型保水剂进行了品种的鉴别研究。结果表明:近红外光谱技术结合SVM法可以有效的进行保水剂分类鉴别工作。当光谱范围选择5000cm-1～9000cm-1,经验参数c=8,g=0.0313时,PCA-SVM模型的预测准确率可以达到100%。研究证明此种方法可以应用于保水剂品种的鉴别。
|
| 关 键 词： | 近红外光谱法 支持向量机 保水剂 高级吸水树脂 |
Study on identification of super absorbent polymer by near infrared reflectance spectroscopy and support vector machine model |
| |
| YUE Zhengwen,WANG Hongliu,CHENG Geer,ZHAO Mingjun,WANG Baitian.Study on identification of super absorbent polymer by near infrared reflectance spectroscopy and support vector machine model[J].Journal of Arid Land Resources and Environment,2012(4):172-175. |
| |
| Authors: | YUE Zhengwen WANG Hongliu CHENG Geer ZHAO Mingjun WANG Baitian |
| |
| Institution: | 1(1.College of Soil and Water Conservation,Beijing Forestry University,Beijing 100083,P.R.China;2.Grassland Resource and Ecology Laboratory,Beijing Forestry University,Beijing 100083,P.R.China;3.College of Ecology and Environmental Science,Inner Mongolia Agricultural University,Huhhot 010017,P.R.China;4.Xuzhou Oil Pipeline Bureau,China Petrochemical Storage Company,Xuzhou 221008,P.R.China) |
| |
| Abstract: | This studies identified the varieties of 24 kinds of Polypropylene-polyacrylamide from different countries and regions by near infrared spectroscopy(NIS) technology companied with four kinds of methods,principal component recession(PCR),partial least squares(PLS),BP neural network,support vector machine.The results showed that method of NIS technology combined with SVM was efficient work on identifying different SAP.Prediction accuracy of PCA-SVM model was got to 100% when spectroscopy scope between 5000cm-1 with 9000cm-1,and experience parameters c=8,g=0.0313.The conclusion is that PCA-SVM model can efficiently apply to identify type of SAP,which is the best prediction model in four methods. |
| |
| Keywords: | near infrared spectroscopy support vector machine super absorbent polymers |
| 本文献已被 CNKI 等数据库收录！ |
|
